An efficient islanding detection method in distributed generation using hybrid SVM-based decision tree
by Gundala Srinivasa Rao; Gattu Keseva Rao
International Journal of Power Electronics (IJPELEC), Vol. 9, No. 2, 2018

Abstract: Islanding is one of the most important concerns of interconnecting the grid-connected distributed resources to the distribution system. At the point when a bit of the distribution system turns out to be electrically detached from the rest of the power system, yet keeps on being empowered by distributed generator (DG) islanding happens. Islanding is an undesirable circumstance, since it is conceivably a hazardous condition for the upkeep work force and might harm the DG and loads on account of unsynchronised reconnection of the lattice because of stage distinction between the grid and DG. So effective and accurate islanding detection is essential to protect the distributed system while landing occurs in a distributed network. In this paper, a hybrid support vector machine with decision-tree classifier is proposed to provide an accurate detection and classification of islanding based on extracted features within less detection time. The proposed method is actualised in MATLAB, and the test results demonstrate the significance and viability of our proposed system than the current islanding discovery strategies.

Online publication date: Tue, 27-Mar-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Power Electronics (IJPELEC):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com